© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4017
    Prev
    Next
    INDEX
    Explanations

    something obvious or hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amat
    -0.11
    uria
    -0.10
    amber
    -0.09
    Unnamed
    -0.09
     disemb
    -0.09
     regret
    -0.09
    ankan
    -0.09
     ster
    -0.09
    uby
    -0.09
    lec
    -0.09
    POSITIVE LOGITS
     staring
    0.27
     right
    0.26
     plain
    0.25
     openly
    0.22
    right
    0.21
     blatantly
    0.21
     blatant
    0.20
     RIGHT
    0.20
     obvious
    0.20
     Plain
    0.20
    Activations Density 0.238%

    No Known Activations